Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs

• URL: http://arxiv.org/abs/2601.12359v1
• Date: Sun, 18 Jan 2026 11:33:35 GMT
• Title: Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs
• Authors: Anirudh Sekar, Mrinal Agarwal, Rachel Sharma, Akitsugu Tanaka, Jasmine Zhang, Arjun Damerla, Kevin Zhu,
• Abstract summary: adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards.<n>We propose Zero-Shot Embedding Drift Detection (ZEDD), a lightweight, low-engineering-overhead framework that identifies both direct and indirect prompt injection attempts.<n>ZEDD operates without requiring access to model internals, prior knowledge of attack types, or task-specific retraining.
• Score: 2.2448294058653455
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful or unintended outputs. Despite advances in alignment, even state-of-the-art LLMs remain broadly vulnerable to adversarial prompts, underscoring the urgent need for robust, productive, and generalizable detection mechanisms beyond inefficient, model-specific patches. In this work, we propose Zero-Shot Embedding Drift Detection (ZEDD), a lightweight, low-engineering-overhead framework that identifies both direct and indirect prompt injection attempts by quantifying semantic shifts in embedding space between benign and suspect inputs. ZEDD operates without requiring access to model internals, prior knowledge of attack types, or task-specific retraining, enabling efficient zero-shot deployment across diverse LLM architectures. Our method uses adversarial-clean prompt pairs and measures embedding drift via cosine similarity to capture subtle adversarial manipulations inherent to real-world injection attacks. To ensure robust evaluation, we assemble and re-annotate the comprehensive LLMail-Inject dataset spanning five injection categories derived from publicly available sources. Extensive experiments demonstrate that embedding drift is a robust and transferable signal, outperforming traditional methods in detection accuracy and operational efficiency. With greater than 93% accuracy in classifying prompt injections across model architectures like Llama 3, Qwen 2, and Mistral and a false positive rate of <3%, our approach offers a lightweight, scalable defense layer that integrates into existing LLM pipelines, addressing a critical gap in securing LLM-powered systems to withstand adaptive adversarial threats.

Related papers

• Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift [23.0914017433021]
  This work identifies a novel class of deployment phase attacks that exploit a vulnerability by injecting imperceptible perturbations directly into the embedding layer outputs without modifying model weights or input text.<n>We propose Search based Embedding Poisoning, a practical, model agnostic framework that introduces carefully optimized perturbations into embeddings associated with high risk tokens.
  arXiv  Detail & Related papers  (2025-09-08T05:00:58Z)
• TopicAttack: An Indirect Prompt Injection Attack via Topic Transition [92.26240528996443]
  Large language models (LLMs) are vulnerable to indirect prompt injection attacks.<n>We propose TopicAttack, which prompts the LLM to generate a fabricated transition prompt that gradually shifts the topic toward the injected instruction.<n>We find that a higher injected-to-original attention ratio leads to a greater success probability, and our method achieves a much higher ratio than the baseline methods.
  arXiv  Detail & Related papers  (2025-07-18T06:23:31Z)
• From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment [4.379304291229695]
  We introduce Refusal-Aware Adaptive Injection (RAAI), a training-free, and model-agnostic framework that repurposes LLM attack techniques.<n> RAAI works by detecting internal refusal signals and adaptively injecting predefined phrases to elicit harmful, yet fluent, completions.<n>Our experiments show RAAI effectively jailbreaks LLMs, increasing the harmful response rate from a baseline of 2.15% to up to 61.04% on average.
  arXiv  Detail & Related papers  (2025-06-07T08:19:01Z)
• Detection Method for Prompt Injection by Integrating Pre-trained Model and Heuristic Feature Engineering [3.0823377252469144]
  prompt injection attacks have emerged as a significant security threat.<n>Existing defense mechanisms face trade-offs between effectiveness and generalizability.<n>We propose a dual-channel feature fusion detection framework.
  arXiv  Detail & Related papers  (2025-06-05T06:01:19Z)
• Robust Anti-Backdoor Instruction Tuning in LVLMs [53.766434746801366]
  We introduce a lightweight, certified-agnostic defense framework for large visual language models (LVLMs)<n>Our framework finetunes only adapter modules and text embedding layers under instruction tuning.<n>Experiments against seven attacks on Flickr30k and MSCOCO demonstrate that ours reduces their attack success rate to nearly zero.
  arXiv  Detail & Related papers  (2025-06-04T01:23:35Z)
• Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs [54.90315421117162]
  We propose a novel poisoning method via completely harmless data.<n>Inspired by the causal reasoning in auto-regressive LLMs, we aim to establish robust associations between triggers and an affirmative response prefix.<n>We observe an interesting resistance phenomenon where the LLM initially appears to agree but subsequently refuses to answer.
  arXiv  Detail & Related papers  (2025-05-23T08:13:59Z)
• Defending against Indirect Prompt Injection by Instruction Detection [109.30156975159561]
  InstructDetector is a novel detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.<n>InstructDetector achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, and reduces the attack success rate to just 0.03% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)
• DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks [87.66245688589977]
  LLM-integrated applications and agents are vulnerable to prompt injection attacks.<n>A detection method aims to determine whether a given input is contaminated by an injected prompt.<n>We propose DataSentinel, a game-theoretic method to detect prompt injection attacks.
  arXiv  Detail & Related papers  (2025-04-15T16:26:21Z)
• Attention Tracker: Detecting Prompt Injection Attacks in LLMs [62.247841717696765]
  Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks.<n>We introduce the concept of the distraction effect, where specific attention heads shift focus from the original instruction to the injected instruction.<n>We propose Attention Tracker, a training-free detection method that tracks attention patterns on instruction to detect prompt injection attacks.
  arXiv  Detail & Related papers  (2024-11-01T04:05:59Z)
• Palisade -- Prompt Injection Detection Framework [0.9620910657090188]
  Large Language Models are vulnerable to malicious prompt injection attacks. This paper proposes a novel NLP based approach for prompt injection detection. It emphasizes accuracy and optimization through a layered input screening process.
  arXiv  Detail & Related papers  (2024-10-28T15:47:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.